© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 16131
    Prev
    Next
    INDEX
    Explanations

    terms related to racing and competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The token "finish" and its related forms

    np_acts-logits-general · gemini-2.0-flash

    finish line and marker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]")]
    -0.61
    WebServlet
    -0.55
    zburg
    -0.53
    RenderAtEndOf
    -0.51
     numberOfRows
    -0.50
     JADX
    -0.50
     continuación
    -0.47
    didSet
    -0.46
    ANGE
    -0.46
    @{
    -0.45
    POSITIVE LOGITS
     finish
    1.33
    finish
    1.22
     finisher
    1.21
     FINISH
    1.17
     Finish
    1.13
     finishing
    1.12
    Finish
    1.11
    Finishing
    1.06
    FINISH
    1.05
     Finishing
    1.05
    Activations Density 0.085%

    No Known Activations